Qwen/Qwen2-Math-72B

Qwen/Qwen2-Math-72B is a 72.7 billion parameter large language model developed by Qwen, specifically designed and optimized for advanced mathematical problem-solving and complex, multi-step logical reasoning. Built upon the Qwen2 LLM series, this model significantly enhances mathematical capabilities, outperforming many open-source and even some closed-source models in arithmetic and mathematical tasks. It is a base model intended for completion and few-shot inference, serving as an excellent starting point for fine-tuning in mathematical domains.